论文信息 - A forecast horizon and a stopping rule for general Markov decision processes - 字舞流文

A forecast horizon and a stopping rule for general Markov decision processes

O. Hernández-Lerma | J. Lasserre

[1] Wallace J. Hopp,et al. Technical Note - Identifying Forecast Horizons in Nonhomogeneous Markov Decision Processes , 1989, Oper. Res..

[2] J. B. Lasserre,et al. Decision Horizon, Overtaking and 1-Optimality Criteria in Optimal Control , 1988 .

[3] Onésimo Hernández-Lerma,et al. Approximation and adaptive control of Markov processes: Average reward criterion , 1987, Kybernetika.

[4] J. Lasserre,et al. An on-line procedure in discounted infinite-horizon stochastic optimal control , 1986 .

[5] Paul J. Schweitzer,et al. Denumerable Undiscounted Semi-Markov Decision Processes with Unbounded Rewards , 1983, Math. Oper. Res..

[6] J. P. Georgin,et al. Estimation et controle des chaines de Markov sur des espaces arbitraires , 1978 .

[7] D. Bertsekas,et al. Dynamic Programming and Stochastic Control , 1977, IEEE Transactions on Systems, Man, and Cybernetics.

[8] James Flynn. Conditions for the Equivalence of Optimality Criteria in Dynamic Programming , 1976 .

[9] Marius Iosifescu,et al. ON TWO RECENT PAPERS ON ERGODICITY IN NONHOMOGENEOUS MARKOV CHAINS , 1972 .

[10] S. Ross. Arbitrary State Markovian Decision Processes , 1968 .